Log inSign up
GitHub
10.9K posts
GitHub profile banner
@github

GitHub

@github
The AI-powered developer platform to build, scale, and deliver secure software.
San Francisco, CA
github.com
Joined February 2008
334
Following
2.7M
Followers
RepliesRepliesRepostsRepostsMediaMediaArticlesArticles

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • Pinned
    @github
    GitHub
    @github
    Sep 4
    4.9 percentage points higher verified task quality. 67% lower estimated cost. Project HydraFusion delivered those results against Claude Opus 5 on Terminal-Bench 2.1 in controlled offline evaluations. HydraFusion orchestrates the models and workflow for each coding task. You
    Image
    Project HydraFusion: Frontier quality via multi-model orchestration
    From github.blog
    38
  • @github
    GitHub
    @github
    5h
    Drop your #GitHubUniverse alias in the replies ⬇️ Don't forget to grab your pass to join us this October githubuniverse.com/?utm_source=Tw…
    Image
    7
  • @github
    GitHub
    @github
    8h
    We're hosting FOUR hours dedicated to how Copilot fits into real developer work. Catch live demos on agent workflows, @code, the GitHub Copilot app and CLI, customization, the new Project HydraFusion, and a lot, lot more. 🚀 Set your reminder for September 10 👇
    Join GitHub Copilot Day
    16
  • @github
    GitHub
    @github
    Sep 5
    ⭐ Track a repo's star growth over time with the new star history REST API endpoint without exposing stargazer identities. Stargazer listing endpoints were restricted to admins and collaborators to protect user privacy. But now you can get insights with this privacy-safe
    Image
    New API endpoint provides privacy-safe star history data - GitHub Changelog
    From github.blog
    14
  • @github
    GitHub
    @github
    Sep 4
    🌌 GPT-6 Astra from @OpenAIDevs is now generally available in GitHub Copilot. This new model is designed for long-horizon, autonomous coding and agentic tasks. Our internal testing shows it plans and validates as it goes, batches diagnosis with verification, and independently
    Image
    00:00
    50
Advertisement
Advertisement